ade irawan - Academia.edu (original) (raw)

Papers by ade irawan

Computatio : Journal of Computer Science and Information Systems

Governments and social media providers put high effort to tackle massive negative contents in soc... more Governments and social media providers put high effort to tackle massive negative contents in social media. Those contents are mostly containing religion, race, and inter-group issues, cyberbullying, and also body shamming, which usually appears together with offensive languages. It becomes difficult to overcome because of a large number of internet users in Indonesia. Hence, we need a system that can automatically detect the negative contents. This paper utilizes Neural Network (NN) models for not only classifying the words as (non)offensive words but also considering the structure of the sentence to get its context. There are two NN models analyzed in this paper: Artificial Neural Network (ANN) and Recurrent Neural Network (RNN). The computer simulation results show that the RNN has better performances than the ANN with the accuracy of training, validation, and testing 94%, 84%, and 84%, respectively. Pemerintah dan penyedia layanan media sosial di Indonesia berusaha keras untuk m...

This thesis proposes an efficient decoding strategy for turbo hybrid automatic repeat request (Tu... more This thesis proposes an efficient decoding strategy for turbo hybrid automatic repeat request (Turbo HARQ). With the new strategy of HARQ protocol based on the turbo principle, it is made possible to combine and decode all (re)transmitted packets in an iterative way. In general, two packet combining schemes are applicable for HARQ: combining-before-decoding (CBD) which is based on the retransmission of the same coded bits, and combining-after-decoding (CAD) which is based on the retransmission of additional redundancy bits produced from an interleaved information version of sequence. This thesis first examines the basic properties of CAD and CBD, and then derives the theoretical limit of the both techniques. It is shown that CAD outperforms CBD. Based on the theoretical limit comparison, this thesis proposes a doped-accumulator assisted CAD technique (ACC-CAD) with different doping rate per transmission phases for practical application. The proposed CAD performs vertical iterations ...

Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer, 2021

Untuk mencapai target konservasi energi sebesar 17% di tahun 2025 pemerintah menerapkan aturan ma... more Untuk mencapai target konservasi energi sebesar 17% di tahun 2025 pemerintah menerapkan aturan management energi bagi industri/penguna energi lebih besar sama dengan 6000 TOE. Di sektor bangunan gedung di Indonesia, konsumsi energi terbesar adalah penggunaan pendingin udara. Salah satu cara untuk melakukan penghematan dalam tata udara dengan menggunakan perangkat yang hemat listrik tanpa mengorbankan kenyamanan penghuni gedung. Penelitian ini menggunakan metode jaringan saraf tiruan untuk memprediksi beban pendingin optimum untuk suatu gedung berdasarkan 8 karakteristik bangunan. Model yang dibuat memberikan hasil yang baik dengan nilai nilai loss 0,4-1,1%

2009 3rd IEEE International Symposium on Microwave, Antenna, Propagation and EMC Technologies for Wireless Communications, 2009

In this paper, we present low complexity down-sampled MMSE channel estimation. We reduced MMSE ch... more In this paper, we present low complexity down-sampled MMSE channel estimation. We reduced MMSE channel estimation complexity by downsampling the MMSE weight matrix. The simulation results show that the bit error rate (BER) performance significantly improved over the least square channel estimation and has comparable BER performance with MMSE channel estimation at low SNR with significant decrease i.e 57% decrease

2009 9th International Symposium on Communications and Information Technology, 2009

Abstract High mobility communication systems need suitable channel estimation to cope high freque... more Abstract High mobility communication systems need suitable channel estimation to cope high frequency selectivity and time variation channel. In recent study on downlink OFDMA mobile WiMAX, channel estimation was done by exploiting pilot from preamble instead of ...

2009 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 2009

Channel estimation is one of key problems in IEEE 802.16e Orthogonal Frequency Division Multiplex... more Channel estimation is one of key problems in IEEE 802.16e Orthogonal Frequency Division Multiplexing Access (OFDMA) downlink system. Minimum Mean Square Error (MMSE) channel estimation has been known as a superior performance channel estimation. However, this algorithm has high computational complexity. In this paper, we present low complexity partial-sampled MMSE channel estimation for compromising between complexity and performance. We reduced

2015 IEEE 82nd Vehicular Technology Conference (VTC2015-Fall), 2015

This paper proposes a Partial Hybrid Automatic Repeat reQuest (P-HARQ) scheme where the relaying ... more This paper proposes a Partial Hybrid Automatic Repeat reQuest (P-HARQ) scheme where the relaying nodes select either forwarding the erroneous packets or requesting retransmission. In contrast to the conventional technique where the erroneous packets is always discarded, the packets found to have errors after decoding are interleaved, re-encoded, and forwarded if relay selects the forwarding mode. This technique is refer to as lossy forwarding. In this paper, the mode selection (either forwarding or requesting retransmission) is based on the confidence indicator (CI). Since the channels are assumed to suffer from block Rayleigh fading, the CI is calculated via online mutual information measurements, block-by-block. Results of computer simulations conducted to confirm the superiority of the proposed P-HARQ technique in terms of bit-error-rate, packeterror-rate and throughput performances in parallel multihop wireless multirelaying systems, are presented.

2019 International Conference of Artificial Intelligence and Information Technology (ICAIIT)

Governments and social media providers put an effort to tackle offensive, abusive, and profanity ... more Governments and social media providers put an effort to tackle offensive, abusive, and profanity in social media as an abuse of speech freedom. Considering the number of Internet user in Indonesia and the conflict caused by offensive content about religion, race, and inter-group issues in Indonesia, there is an urge to develop offensive content detection for posts written in Bahasa. This paper uses an artificial neural network model for not only classifying the words as (non)offensive words but also considering the structure of the sentence to get its context. The challenges are informal grammar and word abbreviation used in social media. Hence, there are noise elimination and normalization processes to address these challenges. The computer simulation results show excellence accuracy of 99.18% training, 94.28% validation, and 96.8% testing, only by utilizing the sigmoid activation function. This model can assist government enforcing the information and electronic transaction law and decreases the number of disputes due to aspiration freedom abuse in social media.

2020 3rd International Conference on Information and Communications Technology (ICOIACT)

Named-Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP) and inf... more Named-Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP) and information extraction. NER is used to extract information such as names of the people, organizations, and places. NER has been used in many fields of work, one of which is in chatbot development. NLP and machine learning approaches enable a smarter chatbot with better personal analysis to users. This research builds a NER model in Indonesian Language using Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Networks (CNNs) model architecture. Unlike the former research, this model only uses word-level embedding in the CNNs layer to keep the model simple. The Named-Entities (NEs) used in this study are limited to the name of the person, organization, location, quantity, and time using the BILOU labeling format. The performance of the model built is measured using micro-averaged f1 score evaluation metric. The BiLSTM-CNNs + pretrained word2vec embedding model provides good performance compared to other models with an f1 score of 71.37%.

2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

This paper proposes a deep-neural-networks scheme for decoding polar coded short packets. We cons... more This paper proposes a deep-neural-networks scheme for decoding polar coded short packets. We consider packet transmission over frequency-flat quasi-static Rayleigh fading channels, where the channel coefficient is constant over a packet but changes packet-by-packet. Potential applications of the proposed technique are machine-type communications, messaging services, smart metering networks, and other wireless sensor networks requiring high reliability and low-latency. Computer simulations results confirm that even with simple codebook construction for an additive white Gaussian noise (AWGN) channel without fading, the proposed technique closes to the theoretical outage and achieves the coding gain in fading channel. Analyses of the learning epochs and training signal-to-noise power ratio (SNR) selections are also presented to demonstrate the effectiveness of the technique.

JITCE (Journal of Information Technology and Computer Engineering)

Excessive use of household electricity is one of the causes of the largest amount of national ele... more Excessive use of household electricity is one of the causes of the largest amount of national electricity consumption coming from households. One way to reduce the amount of household electricity consumption is to automate the operation of electronic devices. This research proposes utilizing Long Short Term Memory (LSTM) algorithm to predict the habit of operating an electronic device. The prediction is then applied to automate the operation of that by exploiting the time series data from the usage. A series of experiments are conducted to capture the data of operating a manual lamp. Then, an LSTM model is built by training the data. The experiment results show the prediction accuracy of 99,28% and Root Mean Square Error of 0,091. Furthermore, the LSTM model is used to automatically operate a lamp in a month. The electricity cost from the automation is 36,38% lower than the manual.

Jurnal Ilmu Komputer dan Informasi

This paper proposes a fully convolutional variational autoencoder (VAE) for features extraction f... more This paper proposes a fully convolutional variational autoencoder (VAE) for features extraction from a large-scale dataset of fire images. The dataset will be used to train the deep learning algorithm to detect fire and smoke. The features extraction is used to tackle the curse of dimensionality, which is the common issue in training deep learning with huge datasets. Features extraction aims to reduce the dimension of the dataset significantly without losing too much essential information. Variational autoencoders (VAEs) are powerfull generative model, which can be used for dimension reduction. VAEs work better than any other methods available for this purpose because they can explore variations on the data in a specific direction.

Proceeding of the Electrical Engineering Computer Science and Informatics

IEEE Transactions on Vehicular Technology

In this paper, we analyze the impact of source correlation on the diversity and coding gains of a... more In this paper, we analyze the impact of source correlation on the diversity and coding gains of a retransmission system where we aim to recover M erroneously received packets only by transmitting one helper packet utilizing the source correlation among the packets. This system is referred to as M-in-1 helper transmission. The helper packet is constructed simply by taking binary exclusive-OR of the M erroneously received information packets, notified via the feedback channel. To identify the trade-off between source correlation and performance gain due to coding and diversity, we start our investigation with in-depth analyses on rate regions and outage probabilities with M = {2, 3}. We also evaluate the influence of unequal power and/or redundancy allocations between the helper and information packets. Finally, we provide the analytical results on achievable diversity order with arbitrary integer values of M. It is shown that M-in-1 helper transmission can always achieve M-th order diversity. Furthermore, (M + 1)-th order diversity can be achieved with M being odd when the source correlation is very high; however, it cannot be achieved with M being even.

Wireless Personal Communications, 2016

This paper proposes Lossy-Forwarding Hybrid Automatic Repeat reQuest (LF-HARQ) schemes to improve... more This paper proposes Lossy-Forwarding Hybrid Automatic Repeat reQuest (LF-HARQ) schemes to improve bit-error-rate (BER), packet-error-rate (PER) and throughput performances of dual-hop wireless parallel relaying systems. In contrast to the conventional lossless decode-and-forward schemes, where erroneous packets are always discarded at the relay, we introduce Lossy-Forwarding concept to HARQ technique that allows the relay nodes to forward them to the next hop, referred to as Fully LF-HARQ (FLF-HARQ) scheme. We then propose Partially LF-HARQ (PLF-HARQ) scheme, where the relaying nodes select either forwarding the erroneous packets or requesting retransmission. The mode selection is based on the confidence indicator (CI) expressing the reliability of the received packets. Since the channels are assumed to suffer from block Rayleigh fading, the CI is calculated via online measurement of mutual information, block-by-block. Results of computer simulations to verify the superiority of the proposed techniques are presented. Keywords hybrid ARQ • lossy forwarding • iterative decoding • relay networks • multihop 1 Introduction Multihop relay networks have long been considered very beneficial for enhancing throughput and coverage of cellular wireless communication systems [1]. Furthermore, it has a ca

2012 International ITG Workshop on Smart Antennas (WSA), 2012

2009 International Conference on Electrical Engineering and Informatics, 2009

Abstract Here we present a new design of a 64-point fast Fourier transform circuit. The design is... more Abstract Here we present a new design of a 64-point fast Fourier transform circuit. The design is derived from Radix-2 3 algorithm and implemented using single path delay feedback architecture. This approach ensures high memory and multiplier utilizations. The ...

2009 International Conference on Electrical Engineering and Informatics, 2009

電子情報通信学会総合大会講演論文集, Feb 28, 2011

抄録: This paper proposes Orthogonal Frequency Division Multiplexing (OFDM) system without guard in... more 抄録: This paper proposes Orthogonal Frequency Division Multiplexing (OFDM) system without guard interval using Chained Turbo Equalization (CHATUE) with a doped accumulator to improve the bit-error-rate (BER) performance. OFDM systems ...